Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xvideos.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse,
   8 )
   9 from ..utils import (
  10     clean_html,
  11     ExtractorError,
  12 )
  13
  14
  15 class XVideosIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
  17     _TEST = {
  18         'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
  19         'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
  20         'info_dict': {
  21             'id': '4588838',
  22             'ext': 'flv',
  23             'title': 'Biker Takes his Girl',
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
  33         if mobj:
  34             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
  35
  36         video_url = compat_urllib_parse.unquote(
  37             self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
  38         video_title = self._html_search_regex(
  39             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
  40         video_thumbnail = self._search_regex(
  41             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
  42
  43         return {
  44             'id': video_id,
  45             'url': video_url,
  46             'title': video_title,
  47             'ext': 'flv',
  48             'thumbnail': video_thumbnail,
  49             'age_limit': 18,
  50         }